BC oasis-audio-pro
Oasis Audio Pro is an AI audio narration generator that transforms your current state of mind, content you want to digest, or recent life events into a personalized audio with BGM. It supports Chinese & English, 9 reference modes (Soul Healing, Daily Briefing, Knowledge Deep Dive, Content Digest, Bedtime Radio, Language Learning, Conversation Extension, Topic Tracker, Study Buddy), and custom audio profiles when no template fits. Use this skill when the user asks to make audio, generate a podcast, turn notes or long content into audio, or when an audio version would add value. This skill includes local Python scripts that read ~/.qclaw or ~/.openclaw session/memory files for personalization — all processing is local and read-only. Only the final composed text prompt is sent to the xplai.ai API (https://eagle-api.xplai.ai); raw conversation history, session files, and USER.md are not transmitted. If the AI judges that the final prompt may be sensitive, the skill shows a sanitized preview and requires a second explicit confirmation before any API request.
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1069 chars, limit 1024
Process rating: all ten parameters 61/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 10 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 33 steps
- 100Failures and branches. 11 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3844 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1069: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 25 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.